| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.031625553447185324, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001265022137887413, | |
| "grad_norm": 35.139339447021484, | |
| "learning_rate": 5e-05, | |
| "loss": 4.1852, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001265022137887413, | |
| "eval_loss": 2.3645200729370117, | |
| "eval_runtime": 4.0111, | |
| "eval_samples_per_second": 12.465, | |
| "eval_steps_per_second": 3.241, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002530044275774826, | |
| "grad_norm": 7.04626989364624, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8438, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003795066413662239, | |
| "grad_norm": 1.121877670288086, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.9922, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005060088551549652, | |
| "grad_norm": 1.3969320058822632, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.0901, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006325110689437065, | |
| "grad_norm": 0.9031108021736145, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.0232, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007590132827324478, | |
| "grad_norm": 0.9523929953575134, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.0277, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008855154965211892, | |
| "grad_norm": 0.9598959684371948, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.0421, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010120177103099304, | |
| "grad_norm": 1.3133834600448608, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.0316, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011385199240986717, | |
| "grad_norm": 10.652119636535645, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.9813, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01265022137887413, | |
| "grad_norm": 2.1253440380096436, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.0884, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013915243516761544, | |
| "grad_norm": 1.9068113565444946, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.1017, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015180265654648957, | |
| "grad_norm": 1.6747380495071411, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.2796, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01644528779253637, | |
| "grad_norm": 29.196680068969727, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 7.4892, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017710309930423784, | |
| "grad_norm": 2.4710311889648438, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.8346, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.018975332068311195, | |
| "grad_norm": 1.579148292541504, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.9865, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02024035420619861, | |
| "grad_norm": 1.1874217987060547, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.8998, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021505376344086023, | |
| "grad_norm": 0.92023766040802, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.8687, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.022770398481973434, | |
| "grad_norm": 0.9192359447479248, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.9686, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02403542061986085, | |
| "grad_norm": 3.2033963203430176, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.1434, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02530044275774826, | |
| "grad_norm": 1.0458755493164062, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.0357, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026565464895635674, | |
| "grad_norm": 1.1212831735610962, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.8479, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.027830487033523088, | |
| "grad_norm": 1.1566752195358276, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.0032, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0290955091714105, | |
| "grad_norm": 1.2244004011154175, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.0365, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.030360531309297913, | |
| "grad_norm": 1.3064579963684082, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.1573, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031625553447185324, | |
| "grad_norm": 1.693029522895813, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.2897, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.031625553447185324, | |
| "eval_loss": 1.932918667793274, | |
| "eval_runtime": 4.0675, | |
| "eval_samples_per_second": 12.293, | |
| "eval_steps_per_second": 3.196, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.087239672233984e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |